A symmetric adaptive visibility graph classification method of orthogonal signals for automatic modulation classification

Visibility graph methods allow time series to mine non‐Euclidean spatial features of sequences by using graph neural network algorithms. Unlike the traditional fixed‐rule‐based univariate time series visibility graph methods, a symmetric adaptive visibility graph method is proposed using orthogonal...

Full description

Saved in:
Bibliographic Details
Published in:IET communications Vol. 17; no. 10; pp. 1208 - 1219
Main Authors: Bai, Haihai, Yang, Jingjing, Huang, Ming, Li, Wenting
Format: Journal Article
Language:English
Published: Stevenage John Wiley & Sons, Inc 01.06.2023
Wiley
Subjects:
Accuracy
Adaptive algorithms
Adaptive sampling
adaptive signal processing
Adaptive visibility graph
Algorithms
Benchmarks
Classification
Communication
Datasets
Deep learning
Fading
Feature extraction
Fourier transforms
Graph neural networks
Graph representations
Hypothesis testing
Mapping
Modulation
modulation classification
neural nets
Neural networks
non‐Euclidean space
orthogonal signals
Quadratures
Radio signals
Sequences
Signal classification
Time series
Visibility
Wavelet transforms
ISSN:1751-8628, 1751-8636
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Visibility graph methods allow time series to mine non‐Euclidean spatial features of sequences by using graph neural network algorithms. Unlike the traditional fixed‐rule‐based univariate time series visibility graph methods, a symmetric adaptive visibility graph method is proposed using orthogonal signals, a method applicable to in‐phase and quadrature (I/Q) orthogonal signals for adaptive graph mapping for radio modulated signals in automatic modulation classification tasks. The method directly models the intra‐channel and inter‐channel graph relations of I/Q signals using two different types of convolutional kernels. It captures non‐Euclidean spatial feature information of I/Q signals using a graph neural network combining graph sampling aggregation and graph differentiable pooling as a feature extractor. Extensive experimental results on two benchmark datasets and a simulated dataset containing channel fading show that the proposed Quadrature Signal Symmetric Adaptive Visibility Graph (QSSAVG) method in this paper outperforms the benchmark method in terms of classification accuracy and is also more robust against channel fading and noise variations. A novel visibility graph classification method of radio modulated signal is proposed in this work, which consists of a Quadrature Signal Symmetric Adaptive Visibility Graph (QSSAVG) algorithm and an end‐to‐end framework of Orthogonal Signal Graph Classification Network (QSGCNet). Extensive experimental results on two benchmark datasets and a simulated dataset containing channel fading show that the proposed QSSAVG method in this paper outperforms the benchmark method in classification accuracy and is also more robust against channel fading and noise variations.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1751-8628
1751-8636
DOI:10.1049/cmu2.12608